GB2610965A - Prediction of performance degradation with non-linear characteristics - Google Patents

Prediction of performance degradation with non-linear characteristics Download PDF

Info

Publication number
GB2610965A
GB2610965A GB2218236.4A GB202218236A GB2610965A GB 2610965 A GB2610965 A GB 2610965A GB 202218236 A GB202218236 A GB 202218236A GB 2610965 A GB2610965 A GB 2610965A
Authority
GB
United Kingdom
Prior art keywords
clusters
score
cluster
anomaly score
data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
GB2218236.4A
Other versions
GB202218236D0 (en
Inventor
Kordjazi Neda
Omolade Saliu Moshood
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
International Business Machines Corp
Original Assignee
International Business Machines Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by International Business Machines Corp filed Critical International Business Machines Corp
Publication of GB202218236D0 publication Critical patent/GB202218236D0/en
Publication of GB2610965A publication Critical patent/GB2610965A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/008—Reliability or availability analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
    • G06F11/302—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system component is a software system
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
    • G06F11/3409—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
    • G06F11/3447—Performance evaluation by modeling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/20—Administration of product repair or maintenance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/04—Billing or invoicing

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Quality & Reliability (AREA)
  • Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Computing Systems (AREA)
  • Development Economics (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Mathematical Physics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Human Resources & Organizations (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Tourism & Hospitality (AREA)
  • Testing And Monitoring For Control Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Steroid Compounds (AREA)
  • Magnetic Ceramics (AREA)
  • Investigating Strength Of Materials By Application Of Mechanical Stress (AREA)
  • Test And Diagnosis Of Digital Computers (AREA)

Abstract

Described are techniques for predicting gradual performance degradation with non-linear characteristics. The techniques including a method comprising inputting a new data sample to a failure prediction model, wherein the failure prediction model is trained using a labeled historical dataset, wherein respective data points are associated with a look-back window and a prediction horizon to create respective training samples, wherein the respective training samples are clustered in a plurality of clusters, and wherein the plurality of clusters are each associated with a normalcy score and an anomaly score. The method further comprises outputting a classification associated with the new data sample based on comparing a first anomaly score of a first cluster of the plurality of clusters that includes the new data sample to an average anomaly score of clusters of the plurality of clusters having the normalcy score greater than the anomaly score.

Claims (34)

1 . A computer-implemented method comprising: inputting a new data sample to a failure prediction model, wherein the failure prediction model is trained using a labeled historical dataset, wherein respective data points are associated with a look-back window and a prediction horizon to create respective training samples, wherein the respective training samples are clustered in a plurality of clusters, and wherein the plurality of clusters are each associated with a normalcy score and an anomaly score; and outputting a classification associated with the new data sample based on comparing a first anomaly score of a first cluster of the plurality of clusters that includes the new data sample to an average anomaly score of clusters of the plurality of clusters having the normalcy score greater than the anomaly score.
2. The method of claim 1 , wherein the classification is indicative of a likelihood of wear-related performance degradation of an asset associated with the new data sample.
3. The method of claim 1 , wherein the look-back window defines a quantity of sequentially previous data points to include in each respective training sample.
4. The method of claim 1 , wherein the prediction horizon defines a predefined amount of time in the future, and wherein respective labels of respective data points the predefined amount of time in the future are associated with the respective training samples.
5. The method of claim 1 , wherein the respective training samples are clustered using K-Means clustering.
6. The method of claim 1 , wherein the method is performed by a failure prediction system according to software that is downloaded to the failure prediction system from a remote data processing system.
7. The method of claim 6, wherein the method further comprises: metering a usage of the software; and generating an invoice based on metering the usage.
8. The method of claim 1 , where the method is for predicting wear-related deterioration of progressing cavity pumps (PCPs), wherein the inputting step comprises inputting a new data sample of a PCP to a model configured to predict wear- related deterioration of the PCP, wherein the model is trained using a labeled historical PCP dataset and wherein the classification outputted during the outputting step is indicative of the wear-related deterioration of the PCP.
9. The method of claim 8 comprising: generating the labeled historical data by performing binary labeling of historical data associated with one or more PCPs, wherein the plurality of training data samples are created by applying a look-back window and a prediction horizon to respective data points of the labeled historical data, wherein the method comprises: calculating cluster scores calculated for respective clusters of the plurality of clusters, said cluster scores being the normalcy score and the anomaly score; assigning the new data sample of a PCP to a first cluster of the plurality of clusters; and assigning a classification to the new data sample based on cluster scores associated with the first cluster.
10. The method of claim 9, wherein the labeled historical data is labeled as faulty for a predetermined period of time prior to a known pump replacement date.
11 . The method of claim 9, wherein the labeled historical data comprises pump speed data, pump torque data, casing pressure data, production rate data, and maintenance records.
12. The method of claim 9, wherein calculating the cluster scores for the respective clusters further comprises: calculating a normalcy score for the first cluster, wherein the normalcy score is a first proportion of training data samples associated with a normal state in the first cluster divided by a second proportion of training data samples associated with the normal state in the plurality of training data samples; and calculating an anomaly score for the first cluster, wherein the anomaly score is a third proportion of training data samples associated with a deteriorated state in the first cluster divided by a fourth proportion of training data samples associated with the deteriorated state in the plurality of training data samples.
13. The method of claim 12, wherein the classification is based on a larger value of the normalcy score or the anomaly score for the first cluster.
14. The method of claim 9, the method further comprising: generating a failure signal for the new data sample, wherein the failure signal comprises an average anomaly score for the new data sample over a predetermined number of prior data points.
15. The method of claim 14, wherein generating the failure signal further comprises: calculating a mean anomaly score for clusters of the plurality of clusters having a normalcy score greater than an anomaly score; for each of the predetermined number of prior data points, associating a one value to data points having an anomaly score of the first cluster greater than the mean anomaly score, and associating a zero value to data points having an anomaly score of the first cluster less than the mean anomaly score; and calculating the failure signal as an average of the one values and zero values associated with each of the predetermined number of prior data points.
16. A system comprising: one or more processors; and one or more computer-readable storage media storing program instructions which, when executed by the one or more processors, are configured to cause the one or more processors to perform a method comprising: inputting a new data sample to a failure prediction model, wherein the failure prediction model is trained using a labeled historical dataset, wherein respective data points are associated with a look-back window and a prediction horizon to create respective training samples, wherein the respective training samples are clustered in a plurality of clusters, and wherein the plurality of clusters are each associated with a normalcy score and an anomaly score; and outputting a classification associated with the new data sample based on comparing a first anomaly score of a first cluster of the plurality of clusters that includes the new data sample to an average anomaly score of clusters in the plurality of clusters having the normalcy score greater than the anomaly score.
17. The system of claim 16, wherein the classification is indicative of a likelihood of wear-related performance degradation of an asset associated with the new data sample.
18. The system of claim 16, wherein the look-back window defines a quantity of sequentially previous data points to include in each respective training sample.
19. The system of claim 16, wherein the prediction horizon defines a predefined amount of time in the future, and wherein respective labels of respective data points the predefined amount of time in the future are associated with the respective training samples.
20. The system of claim 16, wherein the respective training samples are clustered using K-Means clustering.
21 . A computer program product comprising one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions comprising instructions configured to cause one or more processors to perform a method comprising: inputting a new data sample to a failure prediction model, wherein the failure prediction model is trained using a labeled historical dataset, wherein respective data points are associated with a look-back window and a prediction horizon to create respective training samples, wherein the respective training samples are clustered in a plurality of clusters, and wherein the plurality of clusters are each associated with a normalcy score and an anomaly score; and outputting a classification associated with the new data sample based on comparing a first anomaly score of a first cluster of the plurality of clusters that includes the new data sample to an average anomaly score of clusters in the plurality of clusters having the normalcy score greater than the anomaly score.
22. The computer program product of claim 21 , wherein the classification is indicative of a likelihood of wear-related performance degradation of an asset associated with the new data sample.
23. The computer program product of claim 21 , wherein the look-back window defines a quantity of sequentially previous data points to include in each respective training sample.
24. The computer program product of claim 21 , wherein the prediction horizon defines a predefined amount of time in the future, and wherein respective labels of respective data points the predefined amount of time in the future are associated with the respective training samples.
25. The computer program product of claim 21 , wherein the respective training samples are clustered using K-Means clustering.
26. A computer-implemented method for predicting wear-related deterioration of progressing cavity pumps (PCPs), the method comprising: inputting a new data sample of a PCP to a model configured to predict wear-related deterioration of the PCP, wherein the model is trained using a labeled historical PCP dataset, wherein respective data points are associated with a look-back window and a prediction horizon to create respective training samples, wherein the respective training samples are clustered in a plurality of clusters, and wherein the plurality of clusters are each associated with a normalcy score and an anomaly score; and outputting a classification associated with the new data sample based on comparing a first anomaly score of a first cluster of the plurality of clusters that includes the new data sample to an average anomaly score of clusters in the plurality of clusters having the normalcy score greater than the anomaly score, wherein the classification is indicative of the wear- related deterioration of the PCP.
27. A computer-implemented method for predicting wear-related deterioration of progressing cavity pumps (PCPs), the method comprising: generating labeled historical data by performing binary labeling of historical data associated with one or more PCPs; generating a plurality of training data samples by applying a look-back window and a prediction horizon to respective data points of the labeled historical data; clustering the plurality of training data samples into a plurality of clusters; calculating cluster scores for respective clusters of the plurality of clusters; assigning a new data sample of a PCP to a first cluster of the plurality of clusters; and assigning a classification to the new data sample based on cluster scores associated with the first cluster, wherein the classification is indicative of a likelihood of future wear-related deterioration of the PCP.
28. The method of claim 27, wherein the labeled historical data is labeled as faulty for a predetermined period of time prior to a known pump replacement date.
29. The method of claim 27, wherein the labeled historical data comprises pump speed data, pump torque data, casing pressure data, production rate data, and maintenance records.
30. The method of claim 27, wherein calculating the cluster scores for the respective clusters further comprises: calculating a normalcy score for the first cluster, wherein the normalcy score is a first proportion of training data samples associated with a normal state in the first cluster divided by a second proportion of training data samples associated with the normal state in the plurality of training data samples; and calculating an anomaly score for the first cluster, wherein the anomaly score is a third proportion of training data samples associated with a deteriorated state in the first cluster divided by a fourth proportion of training data samples associated with the deteriorated state in the plurality of training data samples.
31 . The method of claim 30, wherein the classification is based on a larger value of the normalcy score or the anomaly score for the first cluster.
32. The method of claim 27, the method further comprising: generating a failure signal for the new data sample, wherein the failure signal comprises an average anomaly score for the new data sample over a predetermined number of prior data points.
33. The method of claim 32, wherein generating the failure signal further comprises: calculating a mean anomaly score for clusters of the plurality of clusters having a normalcy score greater than an anomaly score; for each of the predetermined number of prior data points, associating a one value to data points having an anomaly score of the first cluster greater than the mean anomaly score, and associating a zero value to data points having an anomaly score of the first cluster less than the mean anomaly score; and calculating the failure signal as an average of the one values and zero values associated with each of the predetermined number of prior data points.
34. A computer program comprising program code means adapted to perform the method of any of claims 1 to 15 and any of claims 26 to 33, when said program is run on a computer.
GB2218236.4A 2020-05-11 2021-05-05 Prediction of performance degradation with non-linear characteristics Pending GB2610965A (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US16/871,359 US11175973B1 (en) 2020-05-11 2020-05-11 Prediction of performance degradation with non-linear characteristics
PCT/IB2021/053805 WO2021229371A1 (en) 2020-05-11 2021-05-05 Prediction of performance degradation with non-linear characteristics

Publications (2)

Publication Number Publication Date
GB202218236D0 GB202218236D0 (en) 2023-01-18
GB2610965A true GB2610965A (en) 2023-03-22

Family

ID=78412675

Family Applications (1)

Application Number Title Priority Date Filing Date
GB2218236.4A Pending GB2610965A (en) 2020-05-11 2021-05-05 Prediction of performance degradation with non-linear characteristics

Country Status (10)

Country Link
US (1) US11175973B1 (en)
JP (1) JP2023525959A (en)
KR (1) KR20220154827A (en)
CN (1) CN115699037A (en)
AU (1) AU2021271205B2 (en)
CA (1) CA3175610A1 (en)
DE (1) DE112021002699T5 (en)
GB (1) GB2610965A (en)
IL (1) IL296764A (en)
WO (1) WO2021229371A1 (en)

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11516096B2 (en) * 2020-06-17 2022-11-29 Red Hat, Inc. Automatically managing performance of software in a distributed computing environment
US11651254B2 (en) * 2020-07-07 2023-05-16 Intuit Inc. Inference-based incident detection and reporting
JP2022151193A (en) * 2021-03-26 2022-10-07 横河電機株式会社 Device, method and program
US20230104543A1 (en) * 2021-10-01 2023-04-06 Halliburton Energy Services, Inc. Machine learning based electric submersible pump failure prediction based on data capture at multiple window lengths to detect slow and fast changing behavior
CN114389688B (en) * 2022-01-04 2023-06-13 烽火通信科技股份有限公司 Method and device for predicting performance of optical module
US20230251292A1 (en) * 2022-02-08 2023-08-10 Rohde & Schwarz Gmbh & Co. Kg Data analysis system, measurement device, and method
CN114697203B (en) * 2022-03-31 2023-07-25 浙江省通信产业服务有限公司 Network fault pre-judging method and device, electronic equipment and storage medium
US11563487B1 (en) * 2022-08-19 2023-01-24 Frontier Communications Holdings, Llc Systems and methods for predicting times-to-failure of passive optical network components
FI130824B1 (en) * 2023-01-20 2024-04-09 Nokia Solutions & Networks Oy Method and apparatus for predictive maintenance
CN117469152B (en) * 2023-12-27 2024-04-12 宁德时代新能源科技股份有限公司 Fluid pump abnormality detection method, fluid pump abnormality detection device, electronic device, and storage medium

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150112903A1 (en) * 2013-02-28 2015-04-23 Huawei Technologies Co., Ltd. Defect prediction method and apparatus
US20180137427A1 (en) * 2016-11-17 2018-05-17 Industrial Technology Research Institute Ensemble learning prediction apparatus and method, and non-transitory computer-readable storage medium
CN110276416A (en) * 2019-07-02 2019-09-24 广东省智能机器人研究院 A kind of rolling bearing fault prediction technique
CN110570012A (en) * 2019-08-05 2019-12-13 华中科技大学 Storm-based power plant production equipment fault early warning method and system

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8988236B2 (en) 2010-05-27 2015-03-24 University Of Southern California System and method for failure prediction for rod pump artificial lift systems
US9292799B2 (en) 2013-02-28 2016-03-22 Chevron U.S.A. Inc. Global model for failure prediction for artificial lift systems
US20170096889A1 (en) 2014-03-28 2017-04-06 Schlumberger Technology Corporation System and method for automation of detection of stress patterns and equipment failures in hydrocarbon extraction and production
CA2991725A1 (en) 2018-01-10 2019-07-10 Psi Technologies Inc. Method and apparatus to predict failure and control vibrations in a subsurface artificial lift system
US10975841B2 (en) * 2019-08-02 2021-04-13 Uptake Technologies, Inc. Computer system and method for detecting rotor imbalance at a wind turbine

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150112903A1 (en) * 2013-02-28 2015-04-23 Huawei Technologies Co., Ltd. Defect prediction method and apparatus
US20180137427A1 (en) * 2016-11-17 2018-05-17 Industrial Technology Research Institute Ensemble learning prediction apparatus and method, and non-transitory computer-readable storage medium
CN110276416A (en) * 2019-07-02 2019-09-24 广东省智能机器人研究院 A kind of rolling bearing fault prediction technique
CN110570012A (en) * 2019-08-05 2019-12-13 华中科技大学 Storm-based power plant production equipment fault early warning method and system

Also Published As

Publication number Publication date
GB202218236D0 (en) 2023-01-18
US11175973B1 (en) 2021-11-16
KR20220154827A (en) 2022-11-22
US20210349772A1 (en) 2021-11-11
WO2021229371A1 (en) 2021-11-18
CA3175610A1 (en) 2021-11-18
DE112021002699T5 (en) 2023-03-02
CN115699037A (en) 2023-02-03
JP2023525959A (en) 2023-06-20
IL296764A (en) 2022-11-01
AU2021271205B2 (en) 2024-01-04
AU2021271205A1 (en) 2022-11-10

Similar Documents

Publication Publication Date Title
GB2610965A (en) Prediction of performance degradation with non-linear characteristics
US11036684B2 (en) Columnar database compression
US20230023088A1 (en) System and method for oil and gas predictive analytics
WO2020257782A1 (en) Factory risk estimation using historical inspection data
EP3561759A1 (en) Server, method, and program for supplying desulfurization catalyst-related information, and computer-readable recording medium recording same
US11796991B2 (en) Context-awareness in preventative maintenance
US11030064B2 (en) Facilitating classification of equipment failure data
GB2593604A (en) Prediction model enhancement
US11783414B2 (en) Deep learning approach for assessing credit risk
WO2020257784A1 (en) Inspection risk estimation using historical inspection data
CN112100773A (en) Turbine machinery preventive maintenance method based on component correlation
US11928124B2 (en) Artificial intelligence (AI) based data processing
CN112668749B (en) Coal mine gas early warning method based on class mark weighting extreme learning machine
US20220307945A1 (en) Analysis apparatus, analysis method and computer readable medium
CN115796330A (en) Prediction method, device and storage medium based on Prophet model
CN111008749B (en) Demand prediction method and device
CN112749835A (en) Reservoir productivity prediction method, device and equipment
CN112115573A (en) Method and equipment for evaluating blockage degree of shaft
CN117036008B (en) Automatic modeling method and system for multi-source data
CN117435904B (en) Single feature ordering and composite feature extraction method
JP7275233B1 (en) LEARNING DEVICE, LEARNING METHOD AND LEARNING PROGRAM
US20240259034A1 (en) Compression of a univariate time-series dataset using motifs
US11816427B1 (en) Automated data classification error correction through spatial analysis using machine learning
CN116167532B (en) System optimization method for coal mine industry illegal production behavior prediction system
EP4300503A1 (en) System and method for processing material properties of structural materials